Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to categorization or classification

    oai_token-act-pair · gpt-3.5-turbo

    references to various categories or types of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LAN
    -0.76
    arks
    -0.75
    DS
    -0.71
    BLE
    -0.70
    nut
    -0.69
    ERG
    -0.68
    MEN
    -0.66
     Rings
    -0.66
    ÅĤ
    -0.66
    ERY
    -0.66
    POSITIVE LOGITS
    ãĤ¦ãĤ¹
    0.77
    sort
    0.77
    auld
    0.76
    phabet
    0.75
    entially
    0.72
     sort
    0.68
    furt
    0.67
    ative
    0.66
     sorting
    0.66
    itized
    0.65
    Act Density 0.013%

    No Known Activations